Attila Gere

Is soft independent modeling of class analogies a reasonable choice for supervised pattern recognition

A thorough survey of classification data sets and a rigorous comparison of classification methods clearly show the unambiguous superiority of other techniques over soft independent modeling of class analogies (SIMCA) in the case of classification – which is a frequent area of usage for SIMCA, even though it is a class modeling (one class or disjoint class modeling technique). Two non-parametric methods, sum of ranking differences (SRD) and the generalized pairwise correlation method (GPCM) have been used to rank and group the classifiers obtained from six case studies. Both techniques need a supervisor (a reference) and their results support and validate each other, despite being based on entirely different principles and calculation procedures. To eliminate the effect of the chosen reference, comparisons with one variable (classifier) at a time were calculated and presented as heatmaps. Six case studies show unambiguously that SIMCA is inferior to other classification techniques such as linear and quadratic discriminant analyses, multivariate range modeling, etc. This analysis is similar to meta-analyses frequently applied in medical science nowadays; with the notable difference that we did not (and should not) make any distributional assumptions. A well-founded conclusion can be drawn, as we could not find any circumstances when SIMCA is superior to concurrent techniques. Hence, the question in the title is self-explanatory.

A novel ranking distance measure combining Cayley and Spearman footrule metrics: Combination of Cayley and Spearman's footrule metrics

Defining the appropriate ranking distance measures among rankings is a classic area of study. The goal of our work is to identify a combination of methodologies, which is proven to be capable for the determination of a proper ranking system. In our study, we used 3 well‐established metrics: Kendall tau, Spearman footrule, and Cayley distance and a novel metric created by the combination of Cayley and Spearman footrule metrics. The results of the newly introduced metric depend on how fast we can trade a permutation of items to the reference permutation according to the Spearman footrule. On the other hand, the distance also depends on the number of cycles and the inversions in the cycle. Two case studies—chemometric data of phytonutrients of tomato varieties and sensometric data of orange juices—were used to test the performance of the studied ranking distance metrics. The properties of the new metric were compared to the traditional metrics regarding the normality of their distributions, significant number of differences between the rating objects, and the quality of the rankings. Results were validated by leave‐one‐out cross‐validation and significant differences by Wilcoxon matched pairs test.

Spectral clustering in eye-movement researches: Spectral clustering of eye-movement data

Eye tracking is a widely used technology to capture the eye movements of participants completing different tasks. Several eye‐tracking parameters are measured, which later can be used to characterize the gazing pattern of the individuals. Clustering based on the path walked on by the participants may enable the researchers to create clusters based on the unconscious personality and thinking style. Common clustering methods generally are unable to handle path data; hence, new dynamic variables are needed. Spectral clustering can handle these types of data well. Spectral clustering handles clustering as a graph partitioning problem without making specific assumptions on the form of the clusters and uses eigenvectors of matrices derived from the data. This way, data are mapped to a low‐dimensional space, which can be easily clustered. Different food choice tasks were presented, and each of the 149 participants had to choose 1 product of the presented 4 and later from 8 alternatives. A new measure was introduced based on all 3 consecutive points from the fixations, and the areas of the triangles formed by these 3 points were computed. The new eye‐movement index captures the temporal variation and also considers the orientation of the fixation points. Spectral clustering resulted 5 balanced clusters defined by Dunn, Silhouette, and C‐indices. Results were compared to the most widely applied hierarchical and centroid‐based clustering (k‐means) methods. Spectral clustering achieved the best results in clustering indices and cluster sizes proved to be more balanced; hence, it outperforms the commonly used applied hierarchical and k‐means.

Uncovering Consumer Mindsets Regarding Raw Beverages

Nutritional fads in the health and fitness world are constantly changing. Each new craze has its believers and critics. For the consumer, “what to believe” becomes a topic filled with uncertainty. This paper presents a systematic approach to understanding what consumers believe about the health messaging of “raw beverages”. The paper presents both substantive results from US consumers, as well as demonstrates a general approach by which researchers can more deeply understand the consumer mind with respect to the specifics of health and wellness issues.

Panel performance monitoring by Poincaré plot: A case study on flavoured bottled waters

The application of the Poincaré method is discussed on the field of sensory panel performance monitoring. The Poincaré plot evaluates and visualizes the difference from the consensus for each panelist even for one product and for one attribute. Sensory tests were carried out on 5 commercially available brands of pear-lemon and josta flavoured bottled waters. Several sensory parameters were assessed and a complex dissimilarity index was calculated. Based on this index the attributes and panelists can be ranked highlighting the attribute which was the hardest to evaluate and the most consistent panel member. Our method has been compared to the other methods using the sum of ranking difference method and cross-validated by leave-one-out technique. Regarding both the ranking of the panelists and the ranking of the attributes significant differences were found between the Poincaré method and the traditional techniques since the sum of ranking difference was greater than the critical value of 39 and 79 at 5%, respectively. Only the Poincaré method was able to indicate sweet flavour as the easiest attribute to evaluate. Free R code is available to carry out the calculations and apply this method.

Colour parameters as indicators of lycopene and antioxidant activity traits of cherry tomatoes ( Solanum lycopersicum L .)

There is limited information available on lycopene content and antioxidant activity of new special coloured cherry tomatoes. We also lack data regarding the effects of on the correlation between the commonly applied colour formulas of surface, puree and lycopene content as well as the effect of extraction solvent on the results of antioxidant activity assays. In this study 11 cherry tomatoes including 5 colours (red, bright red, red-green, yellow, orange) from commercial trade were assessed. Surface and puree colours were determined by a hand-top colorimeter using Lab colour space. Lycopene content was measured as well as the FRAP-, DPPH-, CUPRAC-, ABTS- and TPC-assay following extraction by either water, ethanol or methanol. Our results indicate that the most commonly applied formulas are not disturbed by the special coloured varieties. The colour of puree correlated better with the lycopene content than the values measured on the surface. The method-extraction combination ranking showed that the CUPRAC-EtOH and supernatant ones were the best to distinguish cherry tomato samples. Correlation of chromaticity values was strong with the FRAP-assay and with the DPPH-method. We can conclude that colour parameters as indicators of lycopene content are not disturbed by the special coloured varieties and also have some correlation with antioxidant-capacity assays.